© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 107386
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases after nouns

    np_acts-logits-general · gemini-2.5-flash-lite

    imagine and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Opal
    0.51
    ཐ
    0.48
     ujung
    0.48
    ตรวจสอบ
    0.47
    ⌔
    0.47
     Laj
    0.47
    شو
    0.46
     اصلا
    0.46
     Atha
    0.46
     LJ
    0.46
    POSITIVE LOGITS
    他不
    0.51
    小
    0.47
    概念
    0.45
     frightened
    0.45
    ល
    0.45
    ОР
    0.44
    謎
    0.43
    䫝
    0.42
    月
    0.42
     ಮಧ್ಯ
    0.41
    Activations Density 0.001%

    No Known Activations